EUVIMEDEUVIMED entdecken
Crossref

Decentralized and Explainable Brain Tumor Segmentation: A Blockchain-Secured Federated Learning Approach

Aiza Mukhtar, Aamir Ali, Wajiha Farooq, Muhammad Aqib Fareed, Sadia Sohail, Azka Ahsan

ICCK Journal of Image Analysis and Processing · 17.08.2026 · 2 (3) · 168-189

DOI: 10.62762/jiap.2026.354772 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ICCK Journal of Image Analysis and Processing, online erschienen am 17.08.2026. Verfasst von Aiza Mukhtar und 5 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Brain tumor segmentation plays an important role in clinical diagnosis, treatment planning, and neuro-oncology assessment using multimodal Magnetic Resonance Imaging (MRI) data. However, conventional centralized deep learning systems often face limitations associated with patient data privacy, secure inter-institutional collaboration, and limited model interpretability. This study presents a decentralized and privacy-preserving brain tumor segmentation framework that integrates Federated Learning (FL), a blockchain-inspired audit and coordination mechanism, and Explainable Artificial Intelligence (XAI) within a collaborative medical imaging environment. A 3D U-Net architecture was trained on the BraTS 2020 dataset under a simulated multi-institutional federated setting using non-IID MRI data distributions. Federated Averaging (FedAvg) was employed for global model aggregation, while a blockchain-inspired permissioned ledger mechanism was used to record model update hashes and aggregation metadata for auditability across communication rounds. Grad CAM and LIME were incorporated to provide interpretable visualization of tumor related regions contributing to segmentation predictions. Experimental evaluation demonstrated stable convergence behavior with an overall voxel accuracy of 98.52%, a weighted F1 score of 98.3%, and Dice coefficient improvement from 0.752 to 0.830 during federated training. The generated segmentation outputs showed strong agreement with manually annotated tumor regions while preserving decentralized data privacy. The proposed framework contributes a secure, interpretable, and collaborative segmentation pipeline for trustworthy brain tumor analysis across distributed healthcare environments.

Zitieren

APA

Mukhtar, A., Ali, A., Farooq, W., Fareed, M. A., Sohail, S., & Ahsan, A. (2026). Decentralized and Explainable Brain Tumor Segmentation: A Blockchain-Secured Federated Learning Approach. ICCK Journal of Image Analysis and Processing, 2(3), 168-189. https://doi.org/10.62762/jiap.2026.354772

Vancouver

Mukhtar A, Ali A, Farooq W, Fareed MA, Sohail S, Ahsan A. Decentralized and Explainable Brain Tumor Segmentation: A Blockchain-Secured Federated Learning Approach. ICCK Journal of Image Analysis and Processing. 2026;2(3):168-189. doi:10.62762/jiap.2026.354772

BibTeX
@article{Mukhtar2026,
  author = {Mukhtar, Aiza and Ali, Aamir and Farooq, Wajiha and Fareed, Muhammad Aqib and Sohail, Sadia and Ahsan, Azka},
  title = {Decentralized and Explainable Brain Tumor Segmentation: A Blockchain-Secured Federated Learning Approach},
  journal = {ICCK Journal of Image Analysis and Processing},
  year = {2026},
  volume = {2},
  number = {3},
  pages = {168--189},
  doi = {10.62762/jiap.2026.354772}
}
Kostenlos starten →